INDEX

Explanations

words related to transactions or exchanges, such as buying, selling, or passing on items

oai_token-act-pair · gpt-3.5-turbo

specific names and identifiers related to people, relationships, and objects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ü

-0.92

 Haiti

-0.83

 Bened

-0.81

 fundament

-0.79

 Hoffman

-0.75

Hak

-0.73

Jam

-0.72

Hyp

-0.71

Bon

-0.71

iak

-0.71

POSITIVE LOGITS

row

1.31

Row

1.24

 card

1.18

Row

1.14

 Cell

1.13

Card

1.11

 cell

1.10

row

1.08

 Card

1.07

 cards

1.07

Activations Density 0.310%

words related to transactions or exchanges, such as buying, selling, or passing on items

specific names and identifiers related to people, relationships, and objects

No Comments

No Known Activations